adityathedev Goto Github PK

adiexplains

This repository contains code which is taught in Adi Explains coding community :)

adihelps

It is a women safety app.

adityaportfolio

androiddsc

blurremovalusingautoencoders

BlurRemoval-Using-an-Autoencoder Are you poor at taking photos Just like me? Here I have made a Deep learning model using Autoencoder architecture to remove unwanted blur from the image.

braintumorsegmentation-using-transfer-learning

Brain Tumor Segmentation using Transfer learning. Image segmentation is the task of clustering parts of an image together that belong to the same object class. This process is also called pixel-level classification. Brain Tumor Segmentation is a multi-class problem and this model classifies Gliomia tumor, Meningomia Tumor, Pituitary tumor and No tumor with an accuracy of 93%.

breastcancerprediction-using-deepneuralnetwork

Breast Cancer prediction using Deep Neural Network. I got this dataset from UC Irvine medical website. This data set has 32 columns and 569 rows. This model tells you whether your Breast cancer is Malignant or Benign. I have used Keras to build the DeepNeuralNetwork. The neural network has 3 hidden layers which has 512 neurons each. I have used BatchNormalization to standardize the attributes. This model predicts with an accuracy of 93%

calculatorapp

This is a simple calculator app created by using Android Studio. This app can perform all simple operations. Used Java language to develop this app. I created this app to practice my Android Studio.

calculatorusingnodejs

This is a basic calculation website made using Nodejs and ExpressJs. Deployed the website on heroku. Please visit the Master branch for the code https://calculatorusingnodejs.herokuapp.com/

calculatorwebapp

Created a Calculator website using HTML, CSS and JavaScript. This is a fully functional calculator with fantastic CSS UI. It also has slide in animation. The logic of calculator was built using JavaScript,

carfrontend

carpriceprediction

I have used CarDheko's dataset to predict the selling price of the car. I have cleaned the dataset before using. I have implemented Multivariate Regression to predict the Car's price.

chatgpt-chatbot

This repository will guide you to create ChatGPT like chatbot using OpenAI's GPT 3.5 model

commclassroomop

confessionforms

Confession Forms where people can write confessions. My First Web Development project using HTML, CSS and integrated an API to receive the user inputs to my mail.

convolutionalneuralnetwork-to-classify-dogvscat

Convolutional Neural Network to Classify Dogs and Cat. I built a ImageClassifier which classifies and tells you whether its a Dog image or a Cat image. I built a convolutional network which consists of Three Convolution layer and Three MaxPooling layer. Each Convolutional layer has filters, kernel size. Maxpooling layer has stride and pooling size. Then this Convolutional layer Connects to DeepNeuralNetwork. DNN has three hidden layer and output layer having Sigmoid Activation function. I trained this model for 31 epochs and achieved an accuracy of around 85%. I found this massive image dataset online which has 10,028 images(Ten Thousand and Twenty Eight). My model Predicted accurately during the testing phase. I even tested my model using my neighbor dog's pic and it predicted accurately.

convolutionneuralnetwork-to-predict-skincancer

Convolution Neural Network to predict Skin cancer. Skin cancer is considered as one of the most dangerous types of cancers and there is a drastic increase in the rate of deaths due to lack of knowledge on the symptoms and their prevention. Thus, early detection at premature stage is necessary so that one can prevent the spreading of cancer. Skin cancer is further divided into various types out of which the most hazardous ones are Melanoma, Basal cell carcinoma and Squamous cell carcinoma. This project is about detection of skin cancer using machine learning and image processing techniques. This model takes in image as input and tells you whether your skin cancer is Malignant or Benign. I got this dataset online. I trained this model for 25 epochs and achieved an accuracy of 89%. The Convolution Layer extracts the features of the images and is passed through a Deep Neural Network which uses Relu and sigmoid Activation functions to give us the final Output.

covid-19-prediction-using-cnn

Convolution Neural Network to predict Covid-19. This is a CNN model which predicts whether you have Healthy or you have Coronavirus or you have Pneumonia. I implemented CNN from Scratch and I implemented VGG-16 architecture. This model takes your CT scan report as input and will tell you the result. This Convolutional layer Connects to DeepNeuralNetwork. I found this image dataset(CT scan of patients) online and trained the model for 70 epochs using Softmax function in the output layer. If I had got a much more large image dataset(CT scan of patients) then I could have increased the accuracy a bit more. This model has the potential to become a breakthrough invention in the field of medical industry.

covisense

Covid Detection App

covisense.github.io

creditcardfrauddetection-using-deeplearning

CreditCardFraudDetection using Deeplearning. My model achieved an accuracy of 99.83%. I trained my model using Deep Neural Network. This model has six hidden layers. I implemented using keras and tensorflow as backend. It took me around 2 hours to train this model using my laptop's CPU. I got this famous dataset online. This is a massive dataset having 31 columns and 284807 rows. Basically this is a classification problem which tells whether a person has or may commit a fraud based on his details/attributes like Time, amount and other 28 attributes like Time, amount and 29 attributes which is kept confidential by the banks. I have used Adam optimizer for optimization and have used Sigmoid function in the output layer. This model learns the weights using ReLu activation function. The main principle behind this model is the Backpropagation.

customer-management-system

It is a Fullstack application for managing customers which used APIs to perform tasks. It is built using Mongodb,React, Express and Nodejs. It performs all the CRUD operations. I have used axios package manager to interact with the APIs

dakshrecruitmentwebsite

https://adityathedev.github.io/DakshRecruitmentWebsite/

data-preprocessing-in-nlp

A text has undergone the following preprocessing, Convert to lowercase, removing numbers, removing punctuations, removing whitespaces, removing stopwords, stemming and lemmatization

deep-art

Deep Art is deep learning project which uses a content image and a style image. It outputs a content image which is styled by a style image.

deepneuralnetwork-to-predict-the-heart-disease

Deep Neural Network to predict the Heart disease. I have used one hidden layer which contains 1000 neurons. This is a binary classification problem which I implemented using Deep Neural Network which is also known as Artificial Neural Network.

diabetesprediction

Diabetes prediction using various classification algorithms. I did this project to experiment with various classification algorithms such as Logistic Regression, KNeighborsClassifier, RandomForestClassifier and DecisionTreeClassifier to choose the best fit algorithm for the model. I have achieved an accuracy of 77% using Logistic Regression, 80% accuracy using KNeighborsClassifier, 97.7% accuracy using RandomForestClassifier and 98.5% accuracy using DecisionTreeClassifier. Finally I chose DecisionTreeClassifier for prediction Diabetes with an high accuracy. I got this diabetes dataset from kaggle. The dataset has 2000 rows and 9 columns. There are 9 columns with the following attribute ---> Pregnancies, Glucose, BloodPressure, SkinThickness, Insulin, BMI, DiabetesPedigreeFunction, Age and Outcome. I have used several Data analysis and Data Visualization techniques in this project. This model diagnoses with 98.5% accuracy

facegenerationusingvariationalautoencoder

VARIATIONAL AUTOENCODERS are Generative model. A Generative Model is a powerful way of learning any kind of data distribution using unsupervised learning and it has achieved tremendous success over the past few years.

fetalhealthclassification-using-supportvectormachine

Reduction of child mortality is reflected in several of the United Nations' Sustainable Development Goals and is a key indicator of human progress. The UN expects that by 2030, countries end preventable deaths of newborns and children under 5 years of age, with all countries aiming to reduce under‑5 mortality to at least as low as 25 per 1,000 live births. Parallel to notion of child mortality is of course maternal mortality, which accounts for 295 000 deaths during and following pregnancy and childbirth (as of 2017). The vast majority of these deaths (94%) occurred in low-resource settings, and most could have been prevented. In light of what was mentioned above, Cardiotocograms (CTGs) are a simple and cost accessible option to assess fetal health, allowing healthcare professionals to take action in order to prevent child and maternal mortality. The equipment itself works by sending ultrasound pulses and reading its response, thus shedding light on fetal heart rate (FHR), fetal movements, uterine contractions and more.

filetransferusingqr

This was my computer networks project. File transfer from PC to smartphone using QR on the same network